When I reproduce your code, I have met this bug. Have you ever encountered this problem?
File "/home/dh/HDD/guokai/Learning_DualVD/visdialch/utils/semantic_module.py", line 124, in cap_gate_layer
caption = torch.cat((glcap, locap), -1)
RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 1. Got 6 and 500 in dimension 0 at /pytorch/aten/src/THC/generic/THCTensorMath.cu:71
When I reproduce your code, I have met this bug. Have you ever encountered this problem?
File "/home/dh/HDD/guokai/Learning_DualVD/visdialch/utils/semantic_module.py", line 124, in cap_gate_layer caption = torch.cat((glcap, locap), -1) RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 1. Got 6 and 500 in dimension 0 at /pytorch/aten/src/THC/generic/THCTensorMath.cu:71